Google Image Search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint, openWorldHint), the description adds valuable behavioral traits: caching for 30 minutes and the specific output fields. This provides useful operational context for the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise and well-structured: a clear first sentence, followed by focused bullet points for usage and key parameters, and a caching note. No unnecessary text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, usage scenarios, and caching, but lacks details on default parameters (e.g., num_results=5, safe search default) and does not clarify all available enum values. Despite the output schema existing, the incomplete parameter info reduces overall completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema description coverage is 100%, the description's 'Key parameters' list is incomplete and potentially misleading (e.g., omits 'icon', 'stock', 'dominant_color', 'safe', 'num_results'). This could cause the agent to incorrectly assume only listed values are valid, reducing reliability.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Search for images using Google Custom Search API' and specifies return types (URLs, thumbnails, dimensions, source pages). It distinctly differentiates from sibling tools like google_search and google_news_search by focusing on image content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'When to use' section provides explicit scenarios (finding visual content, needing specific formats/sizes/colors). However, it does not mention when not to use or suggest alternative tools, which would strengthen guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.